© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135435
    Prev
    Next
    INDEX
    Explanations

    javascript event handlers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وګټ
    0.40
     shayari
    0.39
    갯
    0.39
     ادا
    0.38
     hv
    0.38
     ador
    0.38
    onate
    0.37
    採取
    0.37
     erecting
    0.36
     acu
    0.36
    POSITIVE LOGITS
    toggle
    0.40
     toggle
    0.40
     Toggle
    0.39
    blum
    0.38
    plain
    0.38
    χ
    0.38
     divert
    0.37
    Ax
    0.37
     Ax
    0.36
    Vx
    0.36
    Activations Density 0.000%

    No Known Activations